# Revelei

Windows · Desktop app · Windows Native

Most AI photo tools upload the picture and hand back the result. Revelei runs the models on your own machine, on the GPU through DirectML or on the CPU: Real-ESRGAN to upscale 2× and 4×, GFPGAN to restore faces, RMBG with ViTMatte to cut out the background, and SCUNet to remove noise. Every model is checked against its SHA-256, and the photo never leaves the PC.

- Platform: Windows 10 1903 or later / 11, x64
- Licence: Apache-2.0
- Product site: https://alegauss.com/revelei/
- Download: https://github.com/alegauss/revelei/releases/latest
- Source: https://github.com/alegauss/revelei

Public numbers as of 2026-11-13: latest release v0.3.0 (2026-10-23).

## What comes next

From docs/ROADMAP.md at b29d4e2.

### Block F — Delivery: README, benchmarks and installers

- 📋 Every published release is still PhotoBoost, and the README sends people to a Revelei installer that does not exist
- 📋 The README and the site describe four photo operations and never say Revelei can create an image from a prompt
- 📋 A visitor who likes Revelei never learns that Modelado turns a photo into a 3D model the same offline way
- 📋 Every first download meets a SmartScreen warning, and the Store, where photo apps are looked for, has no Revelei
- ⏳ No MSIX package exists, so there is nothing to upload to the Store and nothing to install locally to test that path
- 📋 A Store release means typing the listing, uploading screenshots and the package by hand in Partner Center
- 📋 A Store install would download the CUDA engine's native DLLs after certification, code the Store bars apps from fetching
- 📋 Create makes whatever image a prompt asks for, with no filter and no way to report a result, which Store review checks

### Block I — Model manager: catalog, updates and hardware fit

- 🛠 The hardware verdict stays an estimate after a model has run here; this PC's own speed is never shown
- 📋 A model card offers only the recommended quantisation; a larger or smaller one cannot be chosen

### Block J — Generate an image from a prompt

- 💭 A generation that runs out of video or system memory fails instead of retrying in a way that fits
- 📋 A generated image cannot be upscaled, edited or exported, and its prompt and seed are lost once saved
- 💭 The installer carries no generation engine, so a fresh install could not generate even after a model is downloaded

## Recently shipped

- 2026-10-28 · PB80: There is no screen to write a prompt, pick a model and size, and watch an image being generated
- 2026-10-28 · PB79: The catalog lists no text-to-image model, so there is nothing to download for generation
- 2026-10-28 · PB78: Nothing in the app can turn a prompt into pixels: no layer loads a diffusion model, reports its steps or cancels it
- 2026-10-28 · PB77: No engine in Revelei can run a text-to-image diffusion model, let alone one bigger than 8 GB of video memory
- 2026-10-28 · PB75: Models are managed from a flat text list inside About, with one Download everything button
- 2026-10-28 · PB74: Downloaded models can only live in %LOCALAPPDATA%, so a 15 GB model fills the system drive
- 2026-10-28 · PB73: A multi-gigabyte download starts without checking free disk, cannot be queued, and is read twice to hash it
- 2026-10-28 · PB72: Nothing says whether a model will run well, slowly or not at all on this PC before its gigabytes are downloaded

All entries: https://alegauss.com/changelog/revelei/